base_model:
- HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1
- alpindale/WizardLM-2-8x22B
exported_from: NotAiLOL/Knight-Mixtral-WizardLM-140B-MoE
language:
- en
library_name: transformers
quantized_by: mradermacher
tags:
- mergekit
- merge
About
weighted/imatrix quants of https://huggingface.co/NotAiLOL/Knight-Mixtral-WizardLM-140B-MoE
static quants are available at https://huggingface.co/mradermacher/Knight-Mixtral-WizardLM-140B-MoE-GGUF
Usage
If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.
Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|---|---|---|---|
| GGUF | i1-IQ2_M | 45.9 | |
| PART 1 PART 2 | i1-Q2_K | 51.3 | IQ3_XXS probably better |
| PART 1 PART 2 | i1-IQ3_XXS | 54.0 | lower quality |
| PART 1 PART 2 | i1-Q3_K_S | 60.5 | IQ3_XS probably better |
| PART 1 PART 2 | i1-Q3_K_M | 66.7 | IQ3_S probably better |
| PART 1 PART 2 | i1-Q3_K_L | 71.4 | IQ3_M probably better |
| PART 1 PART 2 | i1-IQ4_XS | 74.2 | |
| PART 1 PART 2 | i1-Q4_K_S | 79.1 | optimal size/speed/quality |
| PART 1 PART 2 | i1-Q4_K_M | 84.1 | fast, recommended |
| PART 1 PART 2 PART 3 | i1-Q6_K | 113.6 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):
And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
Thanks
I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time.